<div dir="ltr"><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">CALL FOR CONTRIBUTIONS</span></font></p>
<font><br><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><span>The AutoML</span> Workshop @ ICML 2014</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Beijing, China, June 25/26, 2014</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Web:</span><a href="http://www.bayesianoptimization.org" style="text-decoration:none" target="_blank"><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> </span></a><a href="http://icml2014.automl.org" style="text-decoration:none" target="_blank"><span style="font-family:Arial;color:rgb(17,85,204);background-color:transparent;font-weight:normal;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline">http://icml2014.<span>automl</span>.org</span></a><a href="http://www.bayesianoptimization.org" style="text-decoration:none" target="_blank"><span style="font-family:Arial;color:rgb(17,85,204);background-color:transparent;font-weight:normal;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline"></span></a></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Email: <a href="mailto:icml2014@automl.org" target="_blank">icml2014@<span>automl</span>.org</a></span></font></p>
<font><br><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">----------------------------------------------------------------</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Important Dates:</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Submission deadline: Friday 25 April, 2014 </span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Notification of acceptance: Friday 16 May, 2014</span></font></p>
<font><br><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">----------------------------------------------------------------</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Workshop Overview:</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Machine
learning has achieved considerable success, but this success crucially
relies on human machine learning experts to select appropriate features,
workflows, <span>ML</span> paradigms, algorithms, and
algorithm hyperparameters. Because the complexity of these tasks is
often beyond non-experts, the rapid growth of machine learning
applications has created a demand for machine learning methods that can
be used easily and without expert knowledge. We call the resulting
research area that targets progressive automation of machine learning </span><span style="vertical-align:baseline;font-variant:normal;font-style:italic;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><span>AutoML</span></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">.</span></font></p>
<div>
<font><br><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><span>AutoML</span> aims to automate many different stages of the machine learning process. Relevant topics include:</span></font></p>
</div><font><div><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Model selection, hyper-parameter optimization, and model search</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> <br>
- Representation learning and automatic feature extraction / construction </span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Reusable workflows and automatic generation of workflows</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Meta learning and transfer learning</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatic problem "ingestion" (from raw data and miscellaneous formats)</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Feature coding/transformation to match requirements of different learning algorithms</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatically detecting and handling skewed data and/or missing values</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatic leakage detection</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Matching problems to methods/algorithms (beyond regression and classification)</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatic acquisition of new data (active learning, experimental design)</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></div>
<span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">
- Automatic report writing (providing insight from the automatic data analysis)</span></font><br><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><div>
<span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">
- User interfaces for <span>AutoML</span> (e.g., “</span><span style="vertical-align:baseline;font-variant:normal;font-style:italic;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Turbo Tax</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> for Machine Learning”)</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatic inference and differentiation</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatic selection of evaluation metrics </span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Automatic creation of appropriately sized and stratified train, validation, and test sets</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Parameterless, robust algorithms </span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></div>
<span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">
- Automatic algorithm selection to satisfy time/space constraints at train- or run-time</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br>
- Run-time wrappers to detect data shift and other causes of prediction failure</span><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span><br>
<span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"><br></span></font></p><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">We
encourage contributions in any of these areas. We welcome 2-page
short-form submissions and 6-page long-form submissions. Submissions
should be formatted using JMLR Workshop and Proceedings format (an
example LaTeX file is available on the workshop website </span><a href="http://icml2014.automl.org" style="text-decoration:none" target="_blank"><span style="font-family:Arial;color:rgb(17,85,204);background-color:transparent;font-weight:normal;font-style:normal;font-variant:normal;text-decoration:underline;vertical-align:baseline">icml2014.<span>automl</span>.org</span></a><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">).
We also encourage submissions of previously-published material that is
closely related to the workshop topic (for presentation only).</span></font></p><div>
<font><br><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Confirmed invited speakers:</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Dan Roth: Language designed for novice <span>ML</span> developers </span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Holger Hoos: Programming by Optimization </span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Yoshua Bengio: Representation learning</span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Jasper Snoek: Hyper-parameter optimization </span></font></p>
<p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify"><font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"> - Vikash Masingka: Probabilistic programming<br>
<br>Advisory Committee: James Bergstra, Nando de Freitas, Roman Garnett, Matt Hoffman, Michael Osborne, Alice Zheng</span></font></p><font><br><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal"></span></font><p dir="ltr" style="line-height:1.15;margin-top:0pt;margin-bottom:0pt;text-align:justify">
<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">Organizers: Frank Hutter, Rich Caruana, Rémi Bardenet, Misha Bilenko, Isabelle Guyon,</span></font><i> </i>Balázs Kégl<font><span style="vertical-align:baseline;font-variant:normal;font-style:normal;background-color:transparent;text-decoration:none;font-family:Arial;font-weight:normal">, and Hugo Larochelle</span></font></p>
</div></div>